Reinforcement learning solution for HJB equation arising in constrained optimal control problem.
Biao LuoHuai-Ning WuTingwen HuangDerong LiuPublished in: Neural Networks (2015)
Keyphrases
- optimal control
- hamilton jacobi bellman
- reinforcement learning
- control problems
- dynamic programming
- brownian motion
- stochastic control
- optimal control problems
- control strategy
- infinite horizon
- control law
- approximate dynamic programming
- nonlinear systems
- average cost
- state space
- learning problems
- markov decision processes
- mathematical model
- actor critic